3038 search results - page 90 / 608 » High-Speed Function Approximation |
112
click to vote
CCIA
2005
Springer
15 years 8 months ago
2005
Springer
— This paper proposes a high-level Reinforcement Learning (RL) control system for solving the action selection problem of an autonomous robot. Although the dominant approach, whe...
152
click to vote
AIPS
2006
15 years 3 months ago
2006
Markov decision processes (MDPs) with discrete and continuous state and action components can be solved efficiently by hybrid approximate linear programming (HALP). The main idea ...
122
Voted
JAIR
2010
15 years 28 days ago
2010
This paper deals with value (and Q-) function approximation in deterministic Markovian decision processes (MDPs). A general statistical framework based on the Kalman filtering pa...
208
click to vote
ICDE
2004
IEEE
16 years 3 months ago
2004
IEEE
The past decade has seen a wealth of research on time series representations, because the manipulation, storage, and indexing of large volumes of raw time series data is impractic...
LICS
2005
IEEE
15 years 8 months ago
2005
IEEE
We construct a domain-theoretic calculus for Lipschitz and differentiable functions, which includes addition, subtraction and composition. We then develop a domaintheoretic versio...